INDEX

Explanations

values of currency in cents

oai_token-act-pair · gpt-3.5-turbo

monetary values specified in cents

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Dresden

-0.71

 Hussain

-0.66

 psychiat

-0.65

ework

-0.65

 skelet

-0.64

 Cooperation

-0.64

idth

-0.64

Stud

-0.63

 Planning

-0.62

 Studies

-0.61

POSITIVE LOGITS

 cents

1.21

 apiece

0.91

clair

0.86

heet

0.76

renheit

0.75

imet

0.75

 dollar

0.75

Ĥª

0.75

ï¸ı

0.74

 sterling

0.72

Activations Density 0.016%

values of currency in cents

monetary values specified in cents

No Comments

No Known Activations